© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 44729
    Prev
    Next
    INDEX
    Explanations

    prices or discounts related to products or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.15
    2:0.08
    3:0.05
    4:0.04
    5:0.07
    6:0.04
    7:0.02
    8:0.08
    9:0.08
    10:0.07
    11:0.09
    Negative Logits
    hower
    -1.90
    erity
    -1.82
    milo
    -1.68
    yip
    -1.63
    iless
    -1.55
    washer
    -1.51
    ��
    -1.47
    iera
    -1.45
    lease
    -1.44
    loading
    -1.44
    POSITIVE LOGITS
    /
    1.81
    ��
    1.61
    �
    1.49
     communities
    1.38
     neighborhoods
    1.36
     targets
    1.35
     Torment
    1.34
    �
    1.33
    �
    1.32
     Sell
    1.32
    Activations Density 0.000%

    No Known Activations